Search Results (583)

Purpose: To develop and validate a two-stage system for automated quality assessment of shoulder true-AP radiographs by combining joint localization with quality classification. Materials and Methods: From the MURA “SHOULDER” subset, 2956 anteroposterior images were identified; 59 images with negative–positive inversion, excessive metallic implants, extreme exposure, or presumed fluoroscopy were excluded, yielding a class-balanced set of 2800 images (1400 OK/1400 NG). A YOLOX-based detector localized the glenohumeral joint, and classifiers operated on both whole images and detector-centered crops. To enhance interpretability, we integrated Grad-CAM into both whole-image and local classifiers and assessed attention patterns against radiographic criteria. Results: The detector achieved AP@0.5 = 1.00 and a mean Dice similarity coefficient of 0.967. The classifier attained AUC = 0.977 (F1 = 0.943) on a held-out test set. Heat map analyses indicated anatomically focused attention consistent with expert-defined regions, and coverage metrics favored local over whole-image models. Conclusions: The two-stage, XAI-integrated approach provides accurate and interpretable assessment of shoulder true-AP image quality, aligning model attention with radiographic criteria. Full article

The daily behavioral patterns of giraffes reflect their health status and well-being. Behaviors such as licking, walking, standing, and eating are not only essential components of giraffes’ routine activities but also serve as potential indicators of their mental and physiological conditions. This is particularly relevant in captive environments such as zoos, where certain repetitive behaviors may signal underlying well-being concerns. Therefore, developing an efficient and accurate automated behavior detection system is of great importance for scientific management and welfare improvement. This study proposes a multi-behavior automatic detection method for giraffes based on YOLO11-Pose and the spatial-adaptive two-stream network (SATSN). Firstly, YOLO11-Pose is employed to detect giraffes and estimate the keypoints of their mouths. Observation-Centric SORT (OC-SORT) is then used to track individual giraffes across frames, ensuring temporal identity consistency based on the keypoint positions estimated by YOLO11-Pose. In the SATSN, we propose a region-of-interest extraction strategy for licking behavior to extract local motion features and perform daily behavior classification. In this network, the original 3D ResNet backbone in the slow pathway is replaced with a video transformer encoder to enhance global spatiotemporal modeling, while a Temporal Attention (TA) module is embedded in the fast pathway to improve the representation of fast motion features. To validate the effectiveness of the proposed method, a giraffe behavior dataset consisting of 420 video clips (10 s per clip) was constructed, with 336 clips used for training and 84 for validation. Experimental results show that for the detection tasks of licking, walking, standing, and eating behaviors, the proposed method achieves a mean average precision (mAP) of 93.99%. This demonstrates the strong detection performance and generalization capability of the approach, providing robust support for automated multi-behavior detection and well-being assessment of giraffes. It also lays a technical foundation for building intelligent behavioral monitoring systems in zoos. Full article

Endophytic bacteria play an important role in the growth, stress tolerance, and metabolic function of salt-tolerant peanuts, yet their community assembly across different saline–alkali soils and plant organs remains poorly characterized. In this study, the V3–V4 variable region of the endophytic bacteria 16S rRNA gene in three organs (roots, leaves, and pods) of high-oleic-acid peanut variety Huayu9118 from three saline–alkali locations (Xinjiang, Jilin, and Shandong, China) was analyzed by high-throughput sequencing. A total of 1,360,313 effective sequences yielded 19,449 amplicon sequence variants (ASVs), with Proteobacteria (45.86–84.62%), Bacteroidota (6.52–13.90%), and Actinobacteriota (3.97–10.87%) dominating all samples. Niche strongly influenced microbial diversity: the roots exhibited the highest level of richness (Chao 1/ACE indices), while the leaves showed the greatest diversity (Shannon/Simpson indices) in XJ samples. Significant compositional differences were observed between aerial (leaves) and underground (roots/pods) organs. Geographic location also markedly shaped endophytic communities, with stronger effects in roots and pods than in leaves—a pattern supported by PCoA combined with ANOSIM (R (roots) = 1, R (pods) = 0.874, R (leaves) = 0.336, respectively, p < 0.001). Saline–alkali adaptation led to a marked enrichment of Novosphingobium in roots and pods and of Halomonas in leaves compared to non-saline–alkali-grown peanuts. Furthermore, the endophytic communities within the same organ type varied significantly across the three saline–alkali sites. Redundancy analysis (RDA) identified the key environmental factors shaping bacterial community composition in the root samples from each location: available phosphorus (AP) and sulfate (SO₄²⁻) were the strongest predictors in XJ; available potassium (AK) and chloride (Cl⁻) in DY; and hydrolyzed nitrogen (HN), pH, soil organic matter (SOM), and bicarbonate (HCO₃⁻) in JL. These findings demonstrate that niches and geographical conditions determined the composition and relative abundance of endophytic bacteria in salt-tolerant peanuts, providing new insights into microbial ecological adaptation in saline–alkali ecosystems. Full article

The proliferation of image sharing on social media poses significant privacy risks. Although some previous works have proposed to detect privacy attributes in image sharing, they suffer from the following shortcomings: (1) reliance only on legacy architectures, (2) failure to model the label correlations (i.e., semantic dependencies and co-occurrence patterns among privacy attributes) between privacy attributes, and (3) adoption of static, one-size-fits-all user preference models. To address these, we propose a comprehensive framework for visual privacy protection. First, we establish a new state-of-the-art (SOTA) architecture using modern vision backbones. Second, we introduce Graph Convolutional Networks (GCN) as a classifier head to counter the failure to model label correlations. Third, to replace static user models, we design a dynamic personalization module using Federated Learning (FL) for privacy preservation and Reinforcement Learning (RL) to continuously adapt to individual user preferences. Experiments on the VISPR dataset demonstrate that our approach can outperform the previous work by a substantial margin of 6% in mAP (52.88% vs. 46.88%) and improve the Overall F1-score by 10% (0.770 vs. 0.700). This provides more meaningful and personalized privacy recommendations, setting a new standard for user-centric privacy protection systems. Full article

In the context of China’s “double carbon” goals, examining the spatial–temporal characteristics and influencing factors of the synergistic effect of pollution control and carbon reduction (SEPCR) in the Chengdu–Chongqing region (CCR) is crucial for advancing both air pollution (AP) control and carbon emissions (CE) mitigation. This study uses data on AP and CE from 2007 to 2022 and employs the coupling coordination degree (CCD) model, spatial autocorrelation analysis, and kernel density estimation to investigate the spatial–temporal distribution and dynamic evolution of the CCD between AP and CE in the CCR. Additionally, the Tobit regression model is applied to identify the key factors influencing this synergy. The results indicate that (1) during the study period, the air pollutant equivalents (APE) in the CCR showed a declining trend, while CE continued to increase; (2) the overall level of coupling coordination remained low, exhibiting an evolutionary pattern of initial increase, subsequent decrease, and then recovery, with synergistic effects showing slight improvement but significant fluctuations; (3) the SEPCR in the CCR was generally dispersed, exhibiting no significant spatial autocorrelation. A “core–periphery” structure emerged, with Chongqing and Chengdu as the core and peripheral cities forming low-value zones. Low–low clusters indicative of a “synergy poverty trap” also appeared; (4) economic development (PGDP), openness level (OP), and environmental regulation intensity (ER) are significant positive drivers, while urbanization rate (UR), industrial structure upgrading (IS), and energy consumption intensity (EI) exert significant negative impacts. Full article

Planosols are seasonally waterlogged soils characterized by an abrupt transition from coarse-textured surface horizons to dense, clay-enriched subsoils. Despite the increased agricultural expansion in the Planosol landscapes, these soils have been largely overlooked in Ethiopia. The FAO soil map of Ethiopia (1:200,000 scale) does not recognize the presence of Planosols. In contrast, the more recent digital soil map of Ethiopia, EthoSoilGrids v1.0, at a 250 spatial resolution, was not detailed enough to capture Planosol landscapes, reflecting their historical undersampling in the legacy data. To address this gap, we conducted a thorough mapping and characterization of Planosols in the Omo-Gibe basin, southwestern Ethiopian highlands. Using over 200 auger observations, 74 georeferenced soil profiles, 296 laboratory analyses, and Random Forest modeling, we produced a 30 m-resolution soil-landscape map. Our results show that Planosols cover about 18% of the basin, a substantial extent previously unrecognized in national exploratory maps. Morphologically, these soils exhibit abrupt textural change from the coarse-textured, light grey Ap/Eg horizon (about 30–40 cm thick) to a very clayey, grey–black Bssg/Bt horizon occurring below 40 cm depth. Analytical data on selected parameters show the following pattern: low clay contents (20–29%) and acidic pH (5.2–5.8) with relatively low CEC values (11–26 cmol/kg) in the surface horizons (Ap/Eg), but pronounced clay increase (37–74%), higher bulk density (1.3 g/cm³), higher pH (up to 6.5), and substantially higher CEC (37–47 cmol/kg) in the sub-surface horizons (Bss/Bt). In terms of soil fertility, Planosols are low in SOC, TN, and exchangeable K contents, but micronutrient levels are variable—high in Fe-Mn-Zn and low in B and Cu. The findings confirm the diagnostic features of WRB Planosols and align with regional East African averages, underscoring the reproducibility of our approach. By rectifying long-standing misclassifications and generating fine-scale, field-validated evidence on soil fertility constraints and management options, this study establishes a strong foundation for targeted soil management in Ethiopia. It offers transferable insights for Planosol-dominated agroecosystems across Eastern Africa. Globally, the dataset contributes to enriching the global scientific knowledge and evidence base on Planosols, thereby supporting their improved characterization and management. Full article

The 84K poplar (Populus alba × Populus glandulosa) is a fast-growing hybrid poplar that was introduced from South Korea by the Chinese Academy of Forestry in 1984. To gain deeper insight into the regulatory mechanisms of leaf development in 84K poplar, we performed bulk RNA sequencing and found that numerous members of the AP2/EREBP family exhibited expression changes, suggesting their crucial roles in leaf development. The AP2/EREBP transcription factor family is one of the largest and most conserved gene families in plants. These genes play a crucial role in plant growth, development, and stress responses. In this study, we identified and analyzed 400 AP2/EREBP genes through transcriptome analysis, excluding genes with missing values (NAs) or FPKM < 1, and selected 76 genes based on their expression patterns at different stages of leaf development. The 76 genes were classified into three subfamilies based on phylogenetic analysis and structural domain characteristics: the RAV subfamily, the ERF subfamily, and the AP2 subfamily. Each subfamily shares similar gene structures and motifs while also exhibiting distinct differences. Segmental duplication events may have contributed to the evolution of this gene family. Most of the promoter cis-acting elements are related to light responses, with fewer elements associated with palisade tissues and hormones. Eight genes, selected for their gradually decreasing expression during leaf development, were validated through RT-PCR experiments. Among them, five genes—Pop_G10G022861, Pop_A01G003858, Pop_A01G081120, Pop_A01G074798, and Pop_A07G010900—exhibited a decreasing trend in expression across the three stages of leaf development. Subcellular localization analysis indicated that Pop_A01G003858 and Pop_G11G077730, two randomly selected genes from the eight AP2/EREBP members validated by RT-PCR, are localized in the nucleus. In conclusion, these findings provide valuable insights into the evolutionary relationships of the 73 AP2/EREBP family members in 84K poplar leaves and lay a foundation for future studies on leaf development. Full article

JUNB and JUND are two transcriptional factors (TFs) of increased interest in cancer, regulating the expression of genes associated with survival, proliferation, differentiation, migration, invasion, angiogenesis, adhesion, apoptosis, and cell cycle regulation. Together with c-JUN, they constitute the JUN family of TFs, acting as downstream effectors of the MAPKs, with established roles in carcinogenesis, disease progression, metastasis, and therapy resistance. Their phosphorylation leads to the formation of dimeric complexes with other TFs (from the JUN, FOS, or ATF families), thereby assembling the AP-1 complex, which exerts multifaceted influences on both normal and cancerous cells. JUNB and JUND are credited with both tumor-suppressing and oncogenic roles, since the outcome of their activation relies on the specific cancer type, disease stage, intracellular localization, and the expression of interacting cofactors. This narrative review explores the current understanding of JUNB and JUND roles within urological cancers (prostate, bladder, renal, and testicular cancer) as these malignancies, while distinct, share common genetic and/or environmental risk factors and varying degrees of androgen receptor (AR) dependency. The study discusses commonalities and differences in the expression patterns, mechanisms, and clinical implications of JUNB and JUND across urological cancers, thus highlighting their potential as prevention, diagnosis, prognosis, and treatment targets. Full article

Maritime transport is vital to the global economy, yet the frequency of natural disasters at sea continues to rise, resulting in more persons falling overboard. Therefore, effective maritime search and rescue (SAR) hinges on accurately predicting the probable distribution of drifting victims and on rapidly devising an optimal search plan. Conventional SAR operations either rely on rigid, pre-defined patterns or employ reinforcement-learning techniques that yield non-unique solutions and incur excessive computational time. To overcome these shortcomings, we propose an adaptive SAR framework that integrates three modules: (i) the AP98 maritime-drift model, (ii) Monte Carlo particle simulation, and (iii) a mixed-integer linear programming (MILP) model. First, Monte Carlo particles are propagated through the AP98 model to generate a probability density map of the victim’s location. Subsequently, the MILP model maximizes the cumulative probability of rescue success while minimizing a composite cost index, producing optimal UAV search trajectories solved via Gurobi. Experimental results on a 10 km × 10 km scenario with five UAVs show that, compared with traditional parallel-line search, the proposed MILP approach increases cumulative success probability by 12.4% within the first twelve search steps, eliminates path overlap entirely, and converges in 9.5 s with an optimality gap of 0.79%, thereby demonstrating both efficiency and real-time viability. When MIPFocus (a solver setting in Gurobi that controls the emphasis of the Mixed Integer Programming solver) aims at the optimal solution and uses the parallel solution method at the same time, the best result is achieved. Full article

Background and Objectives: Cone Beam Computed Tomography (CBCT) offers high-resolution, three-dimensional imaging for detecting apical periodontitis (AP) and evaluating the technical quality of endodontic treatments. This study aimed to investigate the diagnostic value of CBCT in identifying endodontic failures and periapical lesions and to explore the clinical patterns associated with these findings in a Romanian patient cohort. Materials and Methods: A retrospective study was conducted on 258 patients (with 876 root canal-treated teeth), all of whom underwent CBCT imaging between October 2024 and April 2025 at a private radiology center in Craiova, Romania. Of the 876 treated teeth, 409 were diagnosed with apical periodontitis. Patients were present for endodontic treatment at the Endodontics Clinic of the Faculty of Dentistry, University of Medicine and Pharmacy of Craiova. With the patients’ consent, 3D radiological examinations were recommended for better case planning and accurate diagnosis. The periapical status and technical parameters of root canal fillings were assessed using the CBCT-PAI index and evaluated by three calibrated observers. Associations with demographic, clinical, and behavioral factors were statistically analyzed. Results: Apical periodontitis was detected in 46.69% of the teeth examined during the study period, with CBCT-PAI score 3 being the most prevalent. Poor root canal obturation quality (underfilling, overfilling, and voids) was significantly associated with periapical pathology. Chronic lesions were more common than acute ones, especially in older patients. The number of teeth with endodontic treatments and no AP, as well as the number of teeth with AP, was significantly lower for patients with acute AP, indicating the more severe impact of chronic AP on the patients’ oral health status. CBCT allowed the precise localization of missed canals and assessment of lesion severity. Conclusions: Within the limits of a retrospective, referral-based cohort, CBCT aided the detection of periapical pathology in root canal-treated teeth (46.69%). These findings do not represent population-based rates but support the selective use of CBCT, in line with current ESE guidance, for complex cases or when conventional imaging is inconclusive. Full article

Multi-label arrhythmia classification from 12-lead ECG signals is a tricky problem, including spatiotemporal feature extraction, feature fusion, and class imbalance. To address these issues, a multi-scale temporal–dynamic graph convolutional with orthogonal gates method, termed MST-DGCN, is proposed for ECG arrhythmia classification. In this method, a temporal–dynamic graph convolution with dynamic adjacency matrices is used to learn spatiotemporal patterns jointly, and an orthogonal gated fusion mechanism is used to eliminate redundancy, so as to strength their complementarity and independence through adjusting the significance of features dynamically. Moreover, a multi-instance learning strategy is proposed to alleviate class imbalance by adjusting the proportion of a few arrhythmia samples through adaptive label allocation. After validating on the St Petersburg INCART dataset under stringent inter-patient settings, the experimental results show that the proposed MST-DGCN method can achieve the best classification performance with an F1-score of 73.66% (+6.2% over prior baseline methods), with concurrent improvements in AUC (70.92%) and mAP (85.24%), while maintaining computational efficiency. Full article

This study explores advanced methods for analyzing the two-parameter alpha-power exponential (APE) distribution using data from a novel generalized progressive hybrid censoring scheme. The APE model is inherently asymmetric, exhibiting positive skewness across all valid parameter values due to its right-skewed exponential base, with the alpha-power transformation amplifying or dampening this skewness depending on the power parameter. The proposed censoring design offers new insights into modeling lifetime data that exhibit non-monotonic hazard behaviors. It enhances testing efficiency by simultaneously imposing fixed-time constraints and ensuring a minimum number of failures, thereby improving inference quality over traditional censoring methods. We derive maximum likelihood and Bayesian estimates for the APE distribution parameters and key reliability measures, such as the reliability and hazard rate functions. Bayesian analysis is performed using independent gamma priors under a symmetric squared error loss, implemented via the Metropolis–Hastings algorithm. Interval estimation is addressed using two normality-based asymptotic confidence intervals and two credible intervals obtained through a simulated Markov Chain Monte Carlo procedure. Monte Carlo simulations across various censoring scenarios demonstrate the stable and superior precision of the proposed methods. Optimal censoring patterns are identified based on the observed Fisher information and its inverse. Two real-world case studies—breast cancer remission times and global oil reserve data—illustrate the practical utility of the APE model within the proposed censoring framework. These applications underscore the model’s capability to effectively analyze diverse reliability phenomena, bridging theoretical innovation with empirical relevance in lifetime data analysis. Full article

Mineral identification technology is a key technology in the construction of intelligent mines. In ore classification and detection, mining scenarios present challenges, such as diverse ore types, significant scale variations, and complex surface textures. Traditional detection models often suffer from insufficient multi-scale feature representation and weak dynamic adaptability, leading to the missed detection of small targets and misclassification of similar minerals. To address these issues, this paper proposes an efficient multi-scale ore classification and detection model, YOLO-EDH. To begin, standard convolution is replaced with deformable convolution, which efficiently captures irregular defect patterns, significantly boosting the model’s robustness and generalization ability. The C3k2 module is then combined with a modified dynamic convolution module, which avoids unnecessary computational overhead while enhancing the flexibility and feature representation. Additionally, a content-guided attention fusion (HGAF) module is introduced before the detection phase, ensuring that the model assigns the correct importance to various feature maps, thereby highlighting the most relevant object details. Experimental results indicate that YOLO-EDH surpasses YOLOv11, improving the precision, recall, and mAP50 by 0.9%, 1.7%, and 1.6%, respectively. In conclusion, YOLO-EDH offers an efficient solution for ore detection in practical applications, with considerable potential for industries like intelligent mine resource sorting and safety production monitoring, showing notable commercial value. Full article

Object detection in synthetic aperture radar (SAR) imagery poses significant challenges due to low resolution, small objects, arbitrary orientations, and complex backgrounds. Standard object detectors often fail to capture sufficient semantic and geometric cues for such tiny targets. To address this issue, a new Convolutional Neural Network (CNN) framework called Deformable Vectorized Detection Network (DVDNet) has been proposed, specifically designed for detecting small, oriented, and densely packed objects in SAR images. The DVDNet consists of Grouped-Deformable Convolution for adaptive receptive field adjustment to diverse object scales, a Local Binary Pattern (LBP) Enhancement Module that enriches texture representations and enhances the visibility of small or camouflaged objects, and a Vector Decomposition Module that enables accurate regression of oriented bounding boxes via learnable geometric vectors. The DVDNet is embedded in a two-stage detection architecture and is particularly effective in preserving fine-grained features critical for mall object localization. The performance of DVDNet is validated on two SAR small target detection datasets, HRSID and SSDD, and it is experimentally demonstrated that it achieves 90.9% mAP on HRSID and 87.2% mAP on SSDD. The generalizability of DVDNet was also verified on the self-built SAR ship dataset and the remote sensing optical dataset HRSC2016. All these experiments show that DVDNet outperforms the standard detector. Notably, our framework shows substantial gains in precision and recall for small object subsets, validating the importance of combining deformable sampling, texture enhancement, and vector-based box representation for high-fidelity small object detection in complex SAR scenes. Full article

Weakly supervised video anomaly detection (WSVAD) aims to identify unusual events using only video-level labels. However, current methods face several key challenges, including ineffective modelling of complex temporal dependencies, indistinct feature boundaries between visually similar normal and abnormal events, and high false alarm rates caused by an inability to distinguish salient events from complex background noise. This paper proposes a novel method that systematically enhances feature representation and discrimination to address these challenges. The proposed method first builds robust temporal representations by employing a hierarchical multi-scale temporal encoder and a position-aware global relation network to capture both local and long-range dependencies. The core of this method is the dual-stream attention-enhanced memory network, which achieves precise discrimination by learning distinct normal and abnormal patterns via dual memory banks, while utilising bidirectional spatial attention to mitigate background noise and focus on salient events before memory querying. The models underwent a comprehensive evaluation utilising solely RGB features on two demanding public datasets, UCF-Crime and XD-Violence. The experimental findings indicate that the proposed method attains state-of-the-art performance, achieving 87.43% AUC on UCF-Crime and 85.51% AP on XD-Violence. This result demonstrates that the proposed “attention-guided prototype matching” paradigm effectively resolves the aforementioned challenges, enabling robust and precise anomaly detection. Full article